A Detailed Review on Challenges and Imperatives of Various CNN Algorithms in Weed Detection
25 Mar 2021-pp 1068-1073
TL;DR: In this paper, a review article presents a brief overview of some significant research efforts in weed detection system by using image processing techniques and convolution neural network in machine learning algorithms, which gives the best performance in some critical situations, such as collected images of different lighting conditions, identification of plant species, overlapped crop with weed and designing an autonomous patch sprayers.
Abstract: Weed is one of the main reason for getting less production in agriculture field. At present, farmers are using herbicides to control the weed but it’s having negative impact on crop production. To increase the crop production, farmers want to reduce the usage of herbicides. One of the machine learning algorithm, convolution neural network used to classify the weed and crop with high accuracy. CNN gives the best performance in some critical situations also, such as collected images of different lighting conditions, identification of plant species, overlapped crop with weed and designing an autonomous patch sprayers. This review article presents a brief overview of some significant research efforts in weed detection system by using image processing techniques and convolution neural network in machine learning algorithms. Not only CNN, this article reviewed different successful machine learning techniques of supervised and unsupervised learning approaches such as support vector machines, random forest and artificial neural network. This paper aims at providing different challenges and imperatives of various convolution neural network algorithms used in weed detection. Finally, compared different convolution neural network architectures and finds the best CNN architecture used for weed identification system with respect to accuracy.
Citations
More filters
TL;DR: In this article , a new balanced and multi-class dataset for groundnut crops with 15 frequent weeds taken under various lighting conditions and at different places with less noise was provided, and the performance with and without freezing the convolutional layers in five pre-trained architectures: AlexNet, VGG-16, VGC-19, ResNet-50, and ResNet101 on the new balanced groundnut weed dataset (16-classes) and the existing balanced corn weed datasets (5-classes).
1 citations
TL;DR: In this paper , a short overview of some significant agricultural research endeavours using convolution neural networks (CNNs) for classification and detection of weeds is presented. But, the authors do not discuss the use of CNNs in the field of agriculture.
Abstract: Weeds are the major source of concern for farmers, who anticipate that weeds may lower crop productivity. Thus, it is essential and vital to detect weeds. Traditional weed classification methods such as hand cultivation with hoes have many hindrances such as labour cost and time consumption. Currently, weed reduction farmers are using herbicides, but they have a negative impact on farmer health as well as on the environment. So, farmers want to lower the use of herbicides. Precise spraying is one of the methods in present-day agriculture to lower the usage of herbicides and to destroy the weeds with the assistance of new technologies. Deep learning approaches are already being employed in a variety of agricultural and farming applications and gave better results. This chapter uses convolution neural networks to provide a short overview of some significant agricultural research endeavours. Different architectures of CNN for classification and detection were used. In the sector of agriculture, the authors have outlined the notion of CNNs.
References
More filters
TL;DR: This review summarized the advances of weed detection using ground-based machine vision and image processing techniques and application of conventional machine learning-based and recently developed deep learning- based approaches for weed detection were presented.
321 citations
TL;DR: This work achieved above 98% accuracy using Convolutional Neural Networks in the detection of broadleaf and grass weeds in relation to soil and soybean, with an accuracy average between all images above 99%.
288 citations
21 May 2018
TL;DR: In this article, a CNN-based semantic segmentation of crop fields was proposed to identify sugar beet plants, weeds, and background based on RGB data, which can be applied to real-time precision farming robots.
Abstract: Precision farming robots, which target to reduce the amount of herbicides that need to be brought out in the fields, must have the ability to identify crops and weeds in real time to trigger weeding actions. In this paper, we address the problem of CNN-based semantic segmentation of crop fields separating sugar beet plants, weeds, and background solely based on RGB data. We propose a CNN that exploits existing vegetation indexes and provides a classification in real time. Furthermore, it can be effectively re-trained to so far unseen fields with a comparably small amount of training data. We implemented and thoroughly evaluated our system on a real agricultural robot operating in different fields in Germany and Switzerland. The results show that our system generalizes well, can operate at around 20 Hz, and is suitable for online operation in the fields.
286 citations
TL;DR: A computer vision system that successfully discriminates between weed patches and crop rows under uncontrolled lighting in real-time and has been shown to produce acceptable results even under very difficult conditions.
242 citations
01 Jan 2018
TL;DR: An approach for dense semantic weed classification with multispectral images collected by a micro aerial vehicle (MAV) using the recently developed encoder–decoder cascaded convolutional neural network, SegNet, that infers dense semantic classes while allowing any number of input image channels and class balancing with sugar beet and weed datasets.
Abstract: Selective weed treatment is a critical step in autonomous crop management as related to crop health and yield. However, a key challenge is reliable and accurate weed detection to minimize damage to surrounding plants. In this letter, we present an approach for dense semantic weed classification with multispectral images collected by a micro aerial vehicle (MAV). We use the recently developed encoder–decoder cascaded convolutional neural network, SegNet, that infers dense semantic classes while allowing any number of input image channels and class balancing with our sugar beet and weed datasets. To obtain training datasets, we established an experimental field with varying herbicide levels resulting in field plots containing only either crop or weed, enabling us to use the normalized difference vegetation index as a distinguishable feature for automatic ground truth generation. We train six models with different numbers of input channels and condition (fine tune) it to achieve $\sim$ 0.8 F1-score and 0.78 area under the curve classification metrics. For the model deployment, an embedded Graphics Processing Unit (GPU) system (Jetson TX2) is tested for MAV integration. Dataset used in this letter is released to support the community and future work.
225 citations